Back to directory

Unified AI System

A self-hosted, protocol-first AI gateway and agent control plane for OpenAI, Anthropic, Gemini, MCP and A2A, turning a rough request into a structured, reviewable prompt before it runs.

Unified AI System

It gives a team one self-hosted surface for OpenAI-compatible SDKs, MCP, A2A, a CLI and HTTP, while keeping provider calls explicit, with virtual keys and token budgets, exact response caching plus an opt-in lexical-approximate similarity layer, and reverse MCP governance that can generate MCP tools from a REST API.

A one-command Docker demo runs entirely with a local fake provider, needing no API key or account, to show deterministic prompt enhancement before a user commits to real provider credentials; a separate tool can verify the tool roster inside a published container image without a Docker daemon or registry login.

It is currently in hardened public preview: the credential-free path is CI-gated and reproducible, while production deployment still requires the operator's own provider staging, HA/DR drills and security review.

More in LLM gateways

See all 106
  • aihappey-ai

    github.com

    A stateless, multi-provider .NET AI gateway exposing normalized OpenAI- and Anthropic-compatible endpoints, managed agents and skills across a very large catalog of models.

  • Subroute

    github.com

    A local AI gateway and desktop control desk that gives coding tools one steady endpoint, so switching between AI subscriptions, API providers and local models doesn't mean reconfiguring every client.

  • AutoBot

    mrveiss.github.io

    A self-hosted AI platform with a small core (RAG plus knowledge-graph memory, a provider-agnostic LLM gateway with fallback, and governance), a lifecycle manager that deploys, operates and scales the underlying infrastructure, and installable modules built on top.